From: Dave Hansen <haveblue@us.ibm.com>
To: Mel Gorman <mel@csn.ul.ie>
Cc: Linux Memory Management List <linux-mm@kvack.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
lhms-devel@lists.sourceforge.net
Subject: Re: [PATCH 4/7] ppc64 - Specify amount of kernel memory at boot time
Date: Thu, 23 Feb 2006 10:15:55 -0800 [thread overview]
Message-ID: <1140718555.8697.73.camel@localhost.localdomain> (raw)
In-Reply-To: <Pine.LNX.4.64.0602231740410.24093@skynet.skynet.ie>
On Thu, 2006-02-23 at 18:01 +0000, Mel Gorman wrote:
> On Thu, 23 Feb 2006, Dave Hansen wrote:
> > OK, back to the hapless system admin using kernelcore. They have a
> > 4-node system with 2GB of RAM in each node for 8GB total. They use
> > kernelcore=1GB. They end up with 4x1GB ZONE_DMA and 4x1GB
> > ZONE_EASYRCLM. Perfect. You can safely remove 4GB of RAM.
> >
> > Now, imagine that the machine has been heavily used for a while, there
> > is only 1 node's memory available, but CPUs are available in the same
> > places as before. So, you start up your partition again have 8GB of
> > memory in one node. Same kernelcore=1GB option. You get 1x7GB ZONE_DMA
> > and 1x1GB ZONE_EASYRCLM. I'd argue this is going to be a bit of a
> > surprise to the poor admin.
> >
>
> That sort of surprise is totally unacceptable but the behaviour of
> kernelcore needs to be consistent on both the x86 and the ppc (any any
> other ar. How about;
>
> 1. kernelcore=X determines the total amount of memory for !ZONE_EASYRCLM
> (be it ZONE_DMA, ZONE_NORMAL or ZONE_HIGHMEM)
Sounds reasonable. But, if you're going to do that, should we just make
it the opposite and explicitly be easy_reclaim_mem=? Do we want the
limit to be set as "I need this much kernel memory", or "I want this
much removable memory". I dunno.
> 2. For every node that can have ZONE_EASYRCLM, split the kernelcore across
> the nodes as a percentage of the node size
>
> Example: 4 nodes, 1 GiB each, kernelcore=512MB
> node 0 ZONE_DMA = 128MB
> node 1 ZONE_DMA = 128MB
> node 2 ZONE_DMA = 128MB
> node 3 ZONE_DMA = 128MB
>
> 2 nodes, 3GiB and 1GIB, kernelcore=512MB
> node 0 ZONE_DMA = 384
> node 1 ZONE_DMA = 128
>
> It gets a bit more complex on NUMA for x86 because ZONE_NORMAL is
> involved but the idea would essentially be the same.
Yes, chopping it up seems like the right thing (or as close as we can
get) to me.
-- Dave
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2006-02-23 18:16 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-02-17 14:15 [PATCH 0/7] Reducing fragmentation using zones v5 Mel Gorman
2006-02-17 14:16 ` [PATCH 1/7] Add __GFP_EASYRCLM flag and update callers Mel Gorman
2006-02-17 14:16 ` [PATCH 2/7] Create the ZONE_EASYRCLM zone Mel Gorman
2006-02-17 14:16 ` [PATCH 3/7] x86 - Specify amount of kernel memory at boot time Mel Gorman
2006-02-17 14:17 ` [PATCH 4/7] ppc64 " Mel Gorman
2006-02-17 17:16 ` Dave Hansen
2006-02-17 19:03 ` Mel Gorman
2006-02-17 19:17 ` Dave Hansen
2006-02-17 19:36 ` Mel Gorman
2006-02-17 21:31 ` Joel Schopp
2006-02-21 14:51 ` Mel Gorman
2006-02-21 17:35 ` Dave Hansen
2006-02-22 16:43 ` Mel Gorman
2006-02-23 16:42 ` Dave Hansen
2006-02-23 17:19 ` Mel Gorman
2006-02-23 17:38 ` Dave Hansen
2006-02-23 18:01 ` Mel Gorman
2006-02-23 18:15 ` Dave Hansen [this message]
2006-02-24 0:15 ` KAMEZAWA Hiroyuki
2006-02-24 9:04 ` Mel Gorman
2006-02-23 17:40 ` Mike Kravetz
2006-02-17 14:17 ` [PATCH 5/7] At boot, determine what zone memory will hot-add to Mel Gorman
2006-02-17 14:17 ` [PATCH 6/7] Allow HugeTLB allocations to use ZONE_EASYRCLM Mel Gorman
2006-02-17 14:18 ` [PATCH 7/7] Add documentation for extra boot parameters Mel Gorman
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1140718555.8697.73.camel@localhost.localdomain \
--to=haveblue@us.ibm.com \
--cc=lhms-devel@lists.sourceforge.net \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mel@csn.ul.ie \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox